Equipping Diffusion Models with Differentiable Spatial Entropy for Low-Light Image Enhancement
This work addresses the challenge of over-smoothed predictions in image restoration for low-light enhancement, offering a novel loss function that improves perceptual quality, though it is incremental as it builds on diffusion models.
The paper tackles the problem of low-light image enhancement by shifting from deterministic pixel-wise loss to a statistical approach using differentiable spatial entropy, achieving superior accuracy and perceptual quality on datasets and the NTIRE 2024 challenge.
Image restoration, which aims to recover high-quality images from their corrupted counterparts, often faces the challenge of being an ill-posed problem that allows multiple solutions for a single input. However, most deep learning based works simply employ l1 loss to train their network in a deterministic way, resulting in over-smoothed predictions with inferior perceptual quality. In this work, we propose a novel method that shifts the focus from a deterministic pixel-by-pixel comparison to a statistical perspective, emphasizing the learning of distributions rather than individual pixel values. The core idea is to introduce spatial entropy into the loss function to measure the distribution difference between predictions and targets. To make this spatial entropy differentiable, we employ kernel density estimation (KDE) to approximate the probabilities for specific intensity values of each pixel with their neighbor areas. Specifically, we equip the entropy with diffusion models and aim for superior accuracy and enhanced perceptual quality over l1 based noise matching loss. In the experiments, we evaluate the proposed method for low light enhancement on two datasets and the NTIRE challenge 2024. All these results illustrate the effectiveness of our statistic-based entropy loss. Code is available at https://github.com/shermanlian/spatial-entropy-loss.